Binocular AR (Augmented Reality) translation glasses for voice and picture recognition

Abstract

The invention discloses binocular AR (Augmented Reality) translation glasses for voice and picture recognition, belongs to the technical field of intelligent hardware, and aims to solve the problems that the existing AR glasses have various functions and complex voice links, the translated text content cannot be effectively displayed on the AR glasses by voice, the call translation cannot be displayed on the AR glasses, and the user experience is poor. Therefore, language communication barriers are caused, an effective channel for solving communication of different languages is lacked, and the working efficiency and the life convenience are reduced. The function is realized by utilizing an AR technology form, and the AR technology is fully utilized to realize conversion from voice to characters. The device has the technical effects that the device can be used in three states of on-line and off-line voice-to-text translation and picture OCR (Optical Character Recognition) translation, audios picked up by the microphone are wirelessly transmitted to a mobile phone through the Bluetooth technology for voice translating and translating, and are fed back and output on the AR glasses through the Bluetooth technology for displaying; pictures shot by the camera module are transmitted to the mobile phone through algorithm compression.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent hardware, and in particular to binocular AR translation glasses for voice and image recognition. Background Art

[0002] As international cooperation continues to deepen, different languages ​​have become an obstacle to communication. In order to solve the timeliness of communication, it is imperative to develop a pair of glasses with voice translation display. Therefore, it is necessary to use current AR glasses technology to quickly understand the content of the other party's speech through voice recognition, translation, and display, thereby improving work efficiency.

[0003] The AR glasses available today have numerous functions and complex voice links. Voice cannot effectively display translated text content on AR glasses, nor can conversation translations be displayed on AR glasses, resulting in language communication barriers and a lack of effective channels for communication in different languages, which reduces work efficiency and convenience in life. Summary of the invention

[0004] To this end, the present invention provides a binocular AR translation glasses with voice and image recognition to solve the above-mentioned problems in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] According to a first aspect of the present invention, a pair of binocular AR translation glasses for voice and image recognition comprises a left temple of the AR glasses, wherein the left temple of the AR glasses is communicatively connected to a Bluetooth chip via a Bluetooth antenna, a left speaker is arranged on the surface of the left temple of the AR glasses, a storage chip is arranged inside the left temple of the AR glasses, one end of the left temple of the AR glasses is connected to a frame, a left AR optical machine is installed on the surface of the frame, a left waveguide is arranged inside the left AR optical machine, a right AR optical machine is installed on the surface of the frame, a right waveguide is arranged inside the right AR optical machine, four microphones are arranged on the surface of the frame, a camera module is arranged on the surface of the frame, one end of the frame is connected to the right temple of the AR glasses, a battery is arranged inside the right temple of the AR glasses, the battery is connected to a charging chip, a right speaker is arranged on the surface of the right temple of the AR glasses, and a USB TYPE-C interface is arranged on the surface of the right temple of the AR glasses.

[0007] Furthermore, the Bluetooth chip connects the left temple of the AR glasses to the mobile phone via a Bluetooth antenna, thereby establishing a transmission channel between the left temple of the AR glasses and the mobile phone APP.

[0008] Furthermore, the four microphones of the frame pick up sounds, the camera module of the frame acquires pictures, and the sounds are synthesized by algorithms and sent to the mobile phone APP via the Bluetooth chip, and the left and right speakers play the audio.

[0009] Furthermore, when in use, when in the state of online voice translation, the mobile phone APP decompresses the audio picked up by the microphone through an algorithm and transmits it to the cloud, transcribes the voice and translates it to the mobile phone.

[0010] Furthermore, when in use, in the voice offline translation state, the mobile phone APP decompresses the audio picked up by the microphone through an algorithm and outputs the language and text set for the voice translation to the mobile phone.

[0011] Furthermore, when performing OCR translation of images during use, the images taken by the camera module are compressed by an algorithm and output to the mobile phone, which recognizes the text in the images and translates it for feedback to the AR glasses for display.

[0012] Furthermore, when in use, the voice can be directly stored in the glasses, and the voice can be post-processed and converted into text to summarize or form a to-do list.

[0013] Furthermore, based on the transmission channel between the left temple of the AR glasses and the mobile phone APP, the translated text is transmitted to the Bluetooth chip on the left temple of the AR glasses through the mobile phone.

[0014] Furthermore, the Bluetooth chip outputs the received translated text to the left AR optical machine and the right AR optical machine, and the translated content is displayed on the left waveguide and the right waveguide.

[0015] Furthermore, connecting the USB TYPE-C interface can charge the battery on the right temple of the AR glasses, and the charging chip is used to manage and regulate power supply, battery charging and power conversion.

[0016] The present invention has the following advantages:

[0017] The device can be used in three states: voice online translation, offline translation, and image OCR translation. When in use, the four microphones of the frame pick up sound, and the camera module of the frame acquires pictures, which are synthesized by an algorithm and sent to the mobile phone APP by the Bluetooth chip. When in the voice online translation state, the mobile phone APP decompresses the audio picked up by the microphone through the algorithm and transmits it to the cloud, transcribes the voice and translates it to the mobile phone; when in the voice offline translation state, the mobile phone APP decompresses the audio picked up by the microphone through the algorithm and outputs the language and text set for the voice translation to the mobile phone; when performing image OCR translation, the picture taken by the camera module is compressed by the algorithm and output to the mobile phone, and the mobile phone recognizes the picture and text and translates it. The translated content is quickly transmitted back to the left temple of the AR glasses through the Bluetooth chip, and the user can intuitively see the text content directly translated by voice on the left and right waveguides, which solves the barriers to communication in different languages ​​and improves work efficiency and convenience in life. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural diagram of the overall front appearance of the device of the present invention;

[0019] Figure 2 This is the overall left side appearance structure diagram of the device of the present invention;

[0020] Figure 3 This is the overall right side appearance structure diagram of the device of the present invention;

[0021] Figure 4 It is a flow chart of the device of the present invention.

[0022] In the picture: 1. Left temple of AR glasses; 2. Bluetooth chip; 3. Bluetooth antenna; 4. Left speaker; 5. Storage chip; 6. Frame; 7. Left AR optical engine; 8. Left waveguide; 9. Right AR optical engine; 10. Right waveguide; 11. Microphone; 12. Camera module; 13. Right temple of AR glasses; 14. Battery; 15. Charging chip; 16. Right speaker; 17. USB TYPE-C interface. DETAILED DESCRIPTION

[0023] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example 1

[0025] like Figures 1 to 3As shown, a binocular AR translation glasses with voice and image recognition in an embodiment of the first aspect of the present invention comprises a left temple 1 of the AR glasses, the left temple 1 of the AR glasses is communicatively connected to the Bluetooth chip 2 via a Bluetooth antenna 3, a left speaker 4 is arranged on the surface of the left temple 1 of the AR glasses, a storage chip 5 is arranged inside the left temple 1 of the AR glasses, one end of the left temple 1 of the AR glasses is connected to a frame 6, a left AR optical machine 7 is installed on the surface of the frame 6, a left waveguide 8 is arranged inside the left AR optical machine 7, a right AR optical machine 9 is installed on the surface of the frame 6, a right waveguide 10 is arranged inside the right AR optical machine 9, four microphones 11 are arranged on the surface of the frame 6, a camera module 12 is arranged on the surface of the frame 6, one end of the frame 6 is connected to a right temple 13 of the AR glasses, a battery 14 is arranged inside the right temple 13 of the AR glasses, a charging chip 15 is connected to the battery 14, a right speaker 16 is arranged on the surface of the right temple 13 of the AR glasses, and a USB TYPE-C interface 17 is arranged on the surface of the right temple 13 of the AR glasses.

[0026] In the above embodiment, it should be noted that connecting the USB TYPE-C interface 17 can charge the battery 14 of the right temple 13 of the AR glasses, the charging chip 15 is used to manage and adjust the power supply, battery charging and power conversion, and the Bluetooth chip 2 connects the left temple 1 of the AR glasses to the mobile phone through the Bluetooth antenna 3 to establish a transmission channel between the left temple 1 of the AR glasses and the mobile phone APP.

[0027] The technical effect achieved by the above embodiment is: the battery 14 provides a power charging function for the right temple 13 of the AR glasses to ensure the normal use of the device, and the left temple 1 of the AR glasses is paired and connected with the mobile phone through the Bluetooth chip 2 to facilitate data transmission.

[0028] Example 2

[0029] like Figures 1 to 3 As shown, a pair of binocular AR translation glasses with voice and image recognition includes all the contents of Example 1. In addition, the four microphones 11 of the frame 6 pick up the sound, the camera module 12 of the frame 6 acquires the picture, and the sound is sent to the mobile phone APP through algorithm synthesis by the Bluetooth chip 2, and the audio is played by the left speaker 4 and the right speaker 16.

[0030] The technical effect achieved by the above embodiment is as follows: the four microphones 11 can increase the sound pickup intensity and improve the sound pickup accuracy by being set in different directions, thereby ensuring the quality of voice pickup and helping to improve the accuracy of voice recognition and translation. The camera module 12 increases the function of shooting, identifying and translating of the device.

[0031] Example 3

[0032] like Figures 1 to 3As shown, a pair of binocular AR translation glasses with voice and image recognition includes all the contents of Example 1. In addition, when in use, when in the voice online translation state, the mobile phone APP decompresses the audio picked up by the microphone 11 through an algorithm and transmits it to the cloud, performs voice transcription and translates it to the mobile phone; when in the voice offline translation state, the mobile phone APP decompresses the audio picked up by the microphone 11 through an algorithm and outputs the language and text set for the voice translation to the mobile phone; when performing image OCR translation, the image taken by the camera module 12 is compressed through an algorithm, the image text is recognized and translated and output to the mobile phone.

[0033] The technical effect achieved by the above embodiment is: the device can be used in three states: voice online translation, offline translation, and image OCR translation. The voice data is transcribed and translated in the mobile phone APP. In the voice offline translation state, the set language can be translated into text even when there is no network connection. During voice online translation and offline translation, the voice data is kept in the mobile phone APP. The text converted from the original voice and the translated text content can be summarized and a to-do list can be generated. The camera module 12 is used to translate the foreign language text information seen.

[0034] Example 4

[0035] like Figures 1 to 3 As shown, a pair of binocular AR translation glasses with voice and image recognition includes all the contents of Example 1. In addition, based on the transmission channel between the left temple 1 of the AR glasses and the mobile phone APP, the translated text is transmitted to the Bluetooth chip 2 on the left temple 1 of the AR glasses through the mobile phone, and the Bluetooth chip 2 outputs the received translated text to the left AR optical machine 7 and the right AR optical machine 9, and the translated content is displayed on the left waveguide 8 and the right waveguide 10.

[0036] The technical effect achieved by the above embodiment is: the translated content on the mobile phone is quickly transmitted back to the left temple 1 of the AR glasses through the Bluetooth chip 2, and the user can intuitively see the text content directly translated from the voice on the left waveguide 8 and the right waveguide 10. The translation function of the device solves the obstacles to communication in different languages ​​and improves work efficiency and convenience in life.

Claims

1. A binocular AR translation glasses with voice and image recognition, characterized by: The invention comprises an AR glasses left temple (1), wherein the AR glasses left temple (1) is connected to a Bluetooth chip (2) via a Bluetooth antenna (3), a left speaker (4) is arranged on the surface of the AR glasses left temple (1), a storage chip (5) is arranged inside the AR glasses left temple (1), one end of the AR glasses left temple (1) is connected to a frame (6), a left AR optical machine (7) is installed on the surface of the frame (6), a left waveguide plate (8) is arranged inside the left AR optical machine (7), and a right AR optical machine ( 9), a right waveguide (10) is arranged inside the right AR optical machine (9), four microphones (11) are arranged on the surface of the frame (6), a camera module (12) is arranged on the surface of the frame (6), one end of the frame (6) is connected to the right temple (13) of the AR glasses, a battery (14) is arranged inside the right temple (13) of the AR glasses, the battery (14) is connected to a charging chip (15), a right speaker (16) is arranged on the surface of the right temple (13) of the AR glasses, and a USB TYPE-C interface (17) is arranged on the surface of the right temple (13) of the AR glasses.

2. The binocular AR translation glasses with voice and image recognition according to claim 1, characterized in that: The Bluetooth chip (2) connects the AR glasses to the mobile phone via the Bluetooth antenna (3), thereby establishing a transmission channel between the AR glasses and the mobile phone APP.

3. The binocular AR translation glasses with voice and image recognition according to claim 1, characterized in that: The four microphones (11) of the frame (6) pick up the sound, the camera module (12) of the frame (6) acquires the picture, the sound is synthesized by the algorithm and sent to the mobile phone APP by the Bluetooth chip (2), and the left speaker (4) and the right speaker (16) play the audio; When in use, in the state of online voice translation, the mobile phone APP decompresses the audio picked up by the microphone (11) through an algorithm and transmits it to the cloud, performs voice transcription and translates it to the mobile phone; When in use, in the voice offline translation state, the mobile phone APP decompresses the audio picked up by the microphone (11) through an algorithm and outputs the language and text set by the voice translation to the mobile phone; When in use, when performing OCR translation of an image, the image taken by the camera module (12) is compressed by an algorithm, output to a mobile phone for image text translation, and then output to the AR glasses for display.

4. The binocular AR translation glasses with voice and image recognition according to claim 1, characterized in that: Based on the transmission channel between the left temple of the AR glasses (1) and the mobile phone APP, the translated content is transmitted to the Bluetooth chip (2) on the left temple of the AR glasses (1) through voice-to-text conversion of the mobile phone.

5. The binocular AR translation glasses with voice and image recognition according to claim 1, characterized in that: The Bluetooth chip (2) outputs the received translated text to the left AR optical machine (7) and the right AR optical machine (9), and the voice-transcribed text and the translated text content can be displayed on the left waveguide plate (8) and the right waveguide plate (10).

6. The binocular AR translation glasses with voice and image recognition according to claim 1, characterized in that: The battery (14) of the right temple (13) of the AR glasses can be charged by connecting the USB TYPE-C interface (17), and the charging chip (15) is used to manage and regulate power supply, battery charging and power conversion.

Images